End-to-End Workflow Automation for Robust Edge AI Systems

Copyright © 2025 1 European Conference on EDGE AI Technologies and Applications - EEAI 20-22 October 2025, Naples, Italy The intersection of imagination and execution, where edge AI learns to create, reason, and act. Copyright © 2025 European Conference on EDGE AI Technologies and Applications - EEAI Milan, Ita20-22 October 2025 Naples, Italy 2 Copyright © 2025 Ovidiu Vermesan, SINTEF AS, Norway End-to-End Workflow Automation for Robust Edge AI Systems Copyright © 2025 Presentation Outline •Edge AI Landscape Evolution •Emergence of Agentic AI •End-to-End Workflow Automation in Edge AI •Agentic Features in Edge AI •Core Agentic Capabilities - Autonomous Edge AI Systems •Frameworks - Data Ingestion, Model Deployment, Orchestration •Governance, Compliance, and Risk Management •Technical and Operational Challenges •Future Directions and Innovation Opportunities •Conclusions 3 Copyright © 2025 Edge AI Landscape Evolution 4 Emergence of agentic AI oSystems that generate insights and autonomously execute multisystem tasks and orchestrate entire workflows with minimal human intervention. Heterogeneous edge devices oSystems requiring interoperability, scalability, minimising latency, enhancing security, and ensuring real-time responsiveness. E2E workflow automation oSystems requiring end-to-end workflow automation frameworks that integrate data ingestion, model training, real-time inferencing, and continuous learning across distributed devices. ❖Technical dimensions (e.g., data pipelines, model deployment on devices with varying compute capabilities, heterogeneous system orchestration, and continuous monitoring) ❖Emergent agentic features (e.g., intent understanding, context-aware learning, autonomous reasoning, and adaptive behaviour) ❖Support for the new wave of autonomous systems. Copyright © 2025 Emergence of Agentic AI 5 Agentic AI marks a paradigm shift from purely generative or predictive systems to those that incorporate autonomous reasoning. Defined by their ability to reason, plan, and act independently in complex, dynamic environments, these systems can process inputs from multiple sources, determine appropriate actions, and reconfigure workflows in situ. Agentic systems originate from a fusion of probabilistic reasoning and deterministic execution, a synthesis that enables them to monitor realtime conditions and take proactive measures without constant human supervision. •The expansion of IoT devices and the need for low-latency decision-making has fostered the development of edge AI. •By processing data locally on a multitude of heterogeneous devices, edge AI systems can deliver near-instantaneous responses, reduce network bandwidth usage, and preserve data privacy. •The integration of these two paradigms, agentic behaviour and edge deployment, require the development of new workflow automation frameworks for orchestrating tasks across dispersed located nodes. Copyright © 2025 End-to-End Workflow Automation in Edge AI 6 Deploying AI models on edge devices, which have limited compute power necessitates techniques such as model quantization, pruning, and knowledge distillation to optimise models for reduced latency and minimal resource usage. As edge AI involves the real-time execution of agentic functions, ensuring that these compressed models can still perform tasks autonomously and accurately is critical. Heterogeneous edge environments have unique challenges in data ingestion due to variable connectivity, diverse data formats, and resourceconstrained devices. New frameworks employ a combination of sensor fusion, real-time data pre-processing, and distributed storage strategies to ensure that data is reliably acquired and standardised. Data normalization processes, including filtering, noise reduction, and feature extraction, applied before inference or learning algorithm is key for providing edge AI E2E workflow automation. Data Ingestion and Preprocessing at the Edge Data Model Deployment on Heterogeneous Devices Copyright © 2025 End-to-End Workflow Automation in Edge AI 7 Monitoring frameworks output precise metrics related to system performance, error rates, and processing latencies. Central to end-to-end workflow automation is the orchestration layer, a management system that coordinates across numerous agents and devices. Orchestration and Workflow Automation Continuous Monitoring and Feedback Loops The layer enables: •Dynamic Task Scheduling: Automatically distributing tasks among available resources. •Inter-Agent Communication: Ensuring agents share context, data, and instructions seamlessly. •Integrated System Monitoring: Continuously tracking task progress, system health, and deployment efficacy. •Automated feedback loops allow the systems to iterate in near real-time, updating operational parameters based on performance data. •The feedback mechanisms facilitate self-correction, enabling the edge system to adapt its workflows or call for human intervention when anomalies are detected. Copyright © 2025 Agentic Features in Edge AI 8 •Autonomous Reasoning and Decision-Making. •Intent Understanding and Proactive Action. •Context-Aware Learning and Adaptive Behaviour. •Synergy Between Agentic Behaviour and Edge AI. Copyright © 2025 Core Agentic Capabilities - Autonomous Edge AI Systems 9 Feature Description Autonomous Reasoning Independent multistep planning and execution. Intent Understanding Interpretation of human and machine commands and proactive adjustments. Context -Aware Learning Adaptive modifications based on historical and real - time data. Copyright © 2025 [email protected] For your attention Copyright © 2025 Thank You Copyright © 2025 Event Organisers 17 SMARTY - Scalable and Quantum Resilient Heterogeneous Edge Computing enabling Trustworthy, focuses on cloud-edge continuum for heterogeneous systems, that protects data-in-transit and data-in-process, employing novel accelerators for quantum resilient communications, confidential computing, and software defined perimeters. https://www.smarty-project.eu/ EdgeAI (Edge AI Technologies for Optimised Performance Embedded Processing) develops new electronic components and systems, processing architectures, connectivity, software, algorithms, and middleware through the combination of microelectronics, edge AI, embedded systems, and edge computing. www.edge-ai-tech.eu EdgeAI NEUROKIT2E SMARTY dAIEDGE dAIEDGE is the European Network of Excellence for distributed, trustworthy, efficient, and scalable AI at the Edge and promotes the application, development, and deployment of Artificial Intelligence (AI) on edge computing platforms. https://daiedge.eu/ NEUROKIT2E (Open source deep learning platform dedicated to Embedded hardware and Europe) proposes a Deep Learning Platform for Embedded Hardware around an established European value chain (AI HW/SW). The solutions developed support neural network design, optimisation, and implementation on constrained HW. https://www.neurokit2e.eu/ NEUROKIT2E Copyright © 2025 Event Organisers 18 REBECCA (Reconfigurable Heterogeneous Highly Parallel Processing Platform for safe and secure AI) aims to democratize the development of edge AI systems and create a complete hardware and software stack centered around a RISC-V CPU, which offer higher performance, energy efficiency, safety, and security than existing systems. www.rebecca-chip.eu TRISTAN aims to expand, mature, and industrialize the European RISC-V ecosystem to compete with commercial options by leveraging the Open-Source community to gain productivity and quality. A European strategy for RISC-V designs will be defined, creating a repository of industrial rate building blocks for SoC designs in various application domains. www.tristan-project.eu CLEVER (Collaborative edge-cLoud continuum and Embedded AI for a Visionary industry of thE futuRe) proposes innovations in hardware accelerators, design stack, and middleware software that revolutionize the ability of edge computing platforms to operate federated, leveraging sparse resources that are coordinated to create a powerful swarm of resources. www.cleverproject.eu SMARTEDGE TRISTAN CLEVER REBECCA The SmartEdge project aims to achieve dynamic integration of decentralized edge intelligence while prioritizing reliability, security, privacy, and scalability. The SmartEdge solution includes a low-code tool programming environment with three main tools: Continuous Semantic Integration, Dynamic Swarm Network, and Low-code Toolchain for Edge Intelligence. https://www.smart-edge.eu/ Copyright © 2025 Event Organisers 19 The objectives of LoLiPoP IoT (Long Life Power Platforms for Internet of Things) are to develop energy harvesting-based innovative Long Life Power Platforms that enable retrofit of wireless sensor network edge devices for asset tracking, condition and performance monitoring. www.lolipop-iot.eu LoLiPoP IoT EdgeAI-Trust AIMS5.0 SC4EU SC4EU is a unique Chips JU "Innovation Action" project to take the supply chain management of semiconductor production in Europe to a new level. A true demand platform, along with its ontology as a formal description of all information within the chain, facilitates close interaction and smooth, transparent collaboration, making even highly complex supply chains resilient, flexible, and agile. https://sc4.eu/ EdgeAI-Trust addresses an advanced, trustworthy edge AI ecosystem through cuttingedge hardware, software, and tools. The project aims to enhance decentralized EdgeAI operations that are secure, reliable, and sustainable. By integrating AI-based algorithms, devices, and APIs, EdgeAI-Trust fosters interoperability and secure data exchange across diverse platforms. from sensor-actuated devices to cloud systems, all within a dynamic zero trust environment. https://www.edgeai-trust.eu/ AIMS5.0 aims to boost the economy by adopting, extending, and implementing AIenabled HW and SW components and systems across the entire industrial value chain. New technologies from IoT and based on Semantic Web ontologies, ML and AI help European manufacturers to shift from Industry 4.0 to Industry 5.0, creating humancentric workplace conditions and a climate-friendly production. https://aims50.eu/ Copyright © 2025 Supporting Organizations 20 The European Technology Platform on Smart Systems Integration is an industrydriven policy initiative, defining research, development and innovation needs as well as policy requirements related to Smart Systems Integration and integrated Microand Nanosystems. The main objective is to develop a vision and to set up a Strategic Research Agenda. www.smart-systems-integration.org Inside Industry Association is the European Technology Platform for research, design and innovation on Intelligent Digital Systems and their applications. The Association is a membership organisation for the European research and innovation actors with more than 200 members and associates from all over Europe. www.inside-association.eu Chips Joint Undertaking supports research, development, innovation, and future manufacturing capacities in the European semiconductor ecosystem. Launched as part of the Chips for Europe Initiative, it confronts semiconductor shortages and strengthens Europe's digital autonomy, engaging a significant EU, national/regional and private industry funding of nearly €11 billion. https://portal.chips-ju.europa.eu/ EU AENEAS EPoSS INSIDE Chips JU AENEAS standing for Association for European NanoElectronics ActivitieS, is an industrial Association, established in 2006, providing unparalleled networking opportunities, policy influence & supported access to funding to all types RD&I participants in the field of micro and nanoelectronics enabled components and systems. https://aeneas-office.org/